Skip to content
@AgentPostmortem

AgentPostmortem

A public registry of documented AI-agent failures, plus the verification, eval, and security tooling built from it.

AgentPostmortem

Every AI agent failure, documented. Plus the verification, eval, and security tooling built from it.

AgentPostmortem is a public registry of documented AI-agent failures at agentpostmortem.com. The rest of this org is the tooling that comes out of reading those cases: scanners that catch unsafe agent and MCP configurations before install, regression harnesses that fail the build when a prompt gets worse, context and token profilers, and reference agent implementations.

Registry

Repo What it is
agentpostmortem The public case registry itself, www.agentpostmortem.com
Casebook-MCP Remote MCP server exposing the registry as tools any agent can query, plus an investigator agent that drafts postmortems from real precedents
Casebook-Chat Streaming chat UI that searches the live registry over MCP and answers with cited case IDs

Security and verification

Repo What it is
MCP-audit Security scanner and linter for MCP servers, 18 rules, SARIF output
Skill-audit Scans agent skills for prompt injection, dangerous shell, secret access, and exfiltration before you install them, 31 rules
Injection-arena Self-hostable prompt-injection challenge game with a leaderboard
Answerproof Tamper-evident receipts for RAG answers, Merkle inclusion proofs and Ed25519 signatures
VaultRAG Permission-aware RAG with access control enforced inside the retrieval query, with a gold-set eval that fails CI on any leak

Eval and CI

Repo What it is
Evalgate Prompt and agent regression CI, a GitHub Action that fails the build when a prompt gets dumber
Tracecase Record agent runs and replay them against prompt and model changes to catch regressions and unsafe tool calls
Voiceeval Evaluation for voice agents: mis-hearing, missing confirmation, latency, barge-in
Agentrace Observability for Claude Code subagents, reads session transcripts and flags results you should not trust

Context and cost

Repo What it is
Ctxlens Context-window profiler for AI agents, shows what is eating your tokens
Ctxtrim Finds the files ballooning your coding-agent context and writes ignore files to cut it
tokencut Measures and cuts the token cost of LLM and agent message payloads, no model calls

Agents and infrastructure

Repo What it is
Bridgekit Scoped MCP server exposing company tools with per-client permission boundaries and an append-only audit log
Webhands Computer-use agent for tools with no usable API, refuses write actions without explicit confirmation
Greenlite Mobile approval cockpit for AI agents, one-tap approve or deny routed back to the agent
Resolvd End-to-end inbox operator that triages, drafts, and acts within policy on inbound support messages
RelayG Support ticket triage agent as a LangGraph state machine with a human-in-the-loop interrupt and SQLite checkpointing
Tenantq Multi-tenant hybrid-search reference on Qdrant, dense plus sparse RRF fusion with Recall@K and p95 benchmarks

Good first issue

Browse every repo at github.com/orgs/AgentPostmortem/repositories and filter a repo's issues by the good first issue label.

Two contributions are always welcome. First, a new documented case in agentpostmortem: a real, sourced agent failure written up in the registry format. Second, a new detection rule for MCP-audit or Skill-audit, ideally with a fixture that fails before the rule and passes after.

Read the CONTRIBUTING.md in the repo you are changing (for example MCP-audit/CONTRIBUTING.md) before opening a pull request.

Popular repositories Loading

  1. agentpostmortem agentpostmortem Public

    Every AI agent failure, documented. Public case registry.

    TypeScript 2 5

  2. VaultRAG VaultRAG Public

    Permission-aware RAG: access control enforced inside the retrieval query, not after it. 56 tests plus a gold-set eval that fails CI on any leak. Delete the ACL predicate and leak rate goes 0% to 81…

    Python 1 2

  3. Skill-audit Skill-audit Public

    Security scanner for agent skills — flags prompt-injection, dangerous shell, secret access, and exfiltration before you install a Claude/agent Skill. 31 rules, SARIF, zero-dep. npx @royalpinto007/s…

    JavaScript 1

  4. Tracecase Tracecase Public

    CI for AI agents. Record agent runs, replay them against prompt and model changes, and catch regressions and unsafe tool calls before they ship. Diffs each suite against its previous run and return…

    TypeScript

  5. Bridgekit Bridgekit Public

    A scoped MCP server exposing company tools (Shopify, Triple Whale, Postgres) to an AI stack with per-client permission boundaries and an append-only audit log. Writes need an explicit scope. Zero r…

    TypeScript

  6. Webhands Webhands Public

    A computer-use agent for the tools that have no usable API. Drives the real dashboard via Cloudflare Browser Rendering, returns clean structured data, and refuses any write action unless you explic…

    TypeScript

Repositories

Showing 10 of 22 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…